🤖 AI Summary
To address data scarcity and inconsistent performance in road network traffic accident prediction, this paper introduces the first large-scale, publicly available U.S. multi-state unified road safety dataset—comprising 9 million crash records—and integrates road network topology with traffic flow features. We propose a Graph Neural Network (GraphSAGE)-based multi-task transfer learning framework that jointly models traffic volume and crash risk while mitigating inter-state label distribution shifts. Experiments show an average absolute error <22% for crash count prediction and an AUROC of 87.3% for crash occurrence classification; ablation studies confirm the substantial contribution of graph-structured features. Our key contributions are: (1) releasing the first standardized, reproducible large-scale road crash benchmark dataset; and (2) designing a multi-task transfer graph learning paradigm explicitly tailored to geographic heterogeneity.
📝 Abstract
We consider the problem of traffic accident analysis on a road network based on road network connections and traffic volume. Previous works have designed various deep-learning methods using historical records to predict traffic accident occurrences. However, there is a lack of consensus on how accurate existing methods are, and a fundamental issue is the lack of public accident datasets for comprehensive evaluations. This paper constructs a large-scale, unified dataset of traffic accident records from official reports of various states in the US, totaling 9 million records, accompanied by road networks and traffic volume reports. Using this new dataset, we evaluate existing deep-learning methods for predicting the occurrence of accidents on road networks. Our main finding is that graph neural networks such as GraphSAGE can accurately predict the number of accidents on roads with less than 22% mean absolute error (relative to the actual count) and whether an accident will occur or not with over 87% AUROC, averaged over states. We achieve these results by using multitask learning to account for cross-state variabilities (e.g., availability of accident labels) and transfer learning to combine traffic volume with accident prediction. Ablation studies highlight the importance of road graph-structural features, amongst other features. Lastly, we discuss the implications of the analysis and develop a package for easily using our new dataset.